| Name | unsloth-zoo JSON |
| Version |
2025.3.16
JSON |
| download |
| home_page | None |
| Summary | Utils for Unsloth |
| upload_time | 2025-03-22 01:04:43 |
| maintainer | None |
| docs_url | None |
| author | Unsloth AI team |
| requires_python | <3.13,>=3.9 |
| license | None |
| keywords |
ai
llm
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
<div align="center">
<a href="https://unsloth.ai"><picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20logo%20white%20text.png">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20logo%20black%20text.png">
<img alt="unsloth logo" src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20logo%20black%20text.png" height="110" style="max-width: 100%;">
</picture></a>
<a href="https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing"><img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/start free finetune button.png" height="48"></a>
<a href="https://discord.gg/unsloth"><img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord button.png" height="48"></a>
<a href="https://ko-fi.com/unsloth"><img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/buy me a coffee button.png" height="48"></a>
### Unsloth Zoo - Utils for Unsloth!
</div>
## ✨ Finetune for Free
All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, Ollama, vLLM or uploaded to Hugging Face.
| Unsloth supports | Free Notebooks | Performance | Memory use |
|-----------|---------|--------|----------|
| **Llama 3.2 (3B)** | [▶️ Start for free](https://colab.research.google.com/drive/1T5-zKWM_5OD21QHwXHiV9ixTRR7k3iB9?usp=sharing) | 2x faster | 60% less |
| **Llama 3.1 (8B)** | [▶️ Start for free](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) | 2x faster | 60% less |
| **Phi-3.5 (mini)** | [▶️ Start for free](https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing) | 2x faster | 50% less |
| **Gemma 2 (9B)** | [▶️ Start for free](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing) | 2x faster | 63% less |
| **Mistral Small (22B)** | [▶️ Start for free](https://colab.research.google.com/drive/1oCEHcED15DzL8xXGU1VTx5ZfOJM8WY01?usp=sharing) | 2x faster | 60% less |
| **Ollama** | [▶️ Start for free](https://colab.research.google.com/drive/1WZDi7APtQ9VsvOrQSSC5DDtxq159j8iZ?usp=sharing) | 1.9x faster | 43% less |
| **Mistral v0.3 (7B)** | [▶️ Start for free](https://colab.research.google.com/drive/1_yNCks4BTD5zOnjozppphh5GzMFaMKq_?usp=sharing) | 2.2x faster | 73% less |
| **ORPO** | [▶️ Start for free](https://colab.research.google.com/drive/11t4njE3c4Lxl-07OD8lJSMKkfyJml3Tn?usp=sharing) | 1.9x faster | 43% less |
| **DPO Zephyr** | [▶️ Start for free](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 43% less |
- **Kaggle Notebooks** for [Llama 3.1 (8B)](https://www.kaggle.com/danielhanchen/kaggle-llama-3-1-8b-unsloth-notebook), [Gemma 2 (9B)](https://www.kaggle.com/code/danielhanchen/kaggle-gemma-7b-unsloth-notebook/), [Mistral (7B)](https://www.kaggle.com/code/danielhanchen/kaggle-mistral-7b-unsloth-notebook)
- Run [Llama 3.2 1B 3B notebook](https://colab.research.google.com/drive/1hoHFpf7ROqk_oZHzxQdfPW9yvTxnvItq?usp=sharing) and [Llama 3.2 conversational notebook](https://colab.research.google.com/drive/1T5-zKWM_5OD21QHwXHiV9ixTRR7k3iB9?usp=sharing)
- Run [Llama 3.1 conversational notebook](https://colab.research.google.com/drive/15OyFkGoCImV9dSsewU1wa2JuKB4-mDE_?usp=sharing) and [Mistral v0.3 ChatML](https://colab.research.google.com/drive/15F1xyn8497_dUbxZP4zWmPZ3PJx1Oymv?usp=sharing)
- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for continued pretraining / raw text
- This [continued pretraining notebook](https://colab.research.google.com/drive/1tEd1FrOXWMnCU9UIvdYhs61tkxdMuKZu?usp=sharing) is for learning another language
- Click [here](https://github.com/unslothai/unsloth/wiki) for detailed documentation for Unsloth.
## 🔗 Links and Resources
| Type | Links |
| ------------------------------- | --------------------------------------- |
| 📚 **Documentation & Wiki** | [Read Our Docs](https://docs.unsloth.ai) |
| <img height="14" src="https://upload.wikimedia.org/wikipedia/commons/6/6f/Logo_of_Twitter.svg" /> **Twitter (aka X)** | [Follow us on X](https://twitter.com/unslothai)|
| 💾 **Installation** | [unsloth/README.md](https://github.com/unslothai/unsloth/tree/main#-installation-instructions)|
| 🥇 **Benchmarking** | [Performance Tables](https://github.com/unslothai/unsloth/tree/main#-performance-benchmarking)
| 🌐 **Released Models** | [Unsloth Releases](https://huggingface.co/unsloth)|
| ✍️ **Blog** | [Read our Blogs](https://unsloth.ai/blog)|
## ⭐ Key Features
- All kernels written in [OpenAI's Triton](https://openai.com/research/triton) language. **Manual backprop engine**.
- **0% loss in accuracy** - no approximation methods - all exact.
- No change of hardware. Supports NVIDIA GPUs since 2018+. Minimum CUDA Capability 7.0 (V100, T4, Titan V, RTX 20, 30, 40x, A100, H100, L40 etc) [Check your GPU!](https://developer.nvidia.com/cuda-gpus) GTX 1070, 1080 works, but is slow.
- Works on **Linux** and **Windows** via WSL.
- Supports 4bit and 16bit QLoRA / LoRA finetuning via [bitsandbytes](https://github.com/TimDettmers/bitsandbytes).
- Open source trains 5x faster - see [Unsloth Pro](https://unsloth.ai/) for up to **30x faster training**!
- If you trained a model with 🦥Unsloth, you can use this cool sticker! <img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/made with unsloth.png" height="50" align="center" />
## 💾 Installation Instructions
These are utilities for [Unsloth](https://github.com/unslothai/unsloth), so install Unsloth as well! For stable releases for Unsloth Zoo, use `pip install unsloth_zoo`. We recommend `pip install "unsloth_zoo @ git+https://github.com/unslothai/unsloth-zoo.git"` for most installations though.
```bash
pip install unsloth_zoo
```
## License
Unsloth Zoo is licensed under the GNU Affero General Public License.
Raw data
{
"_id": null,
"home_page": null,
"name": "unsloth-zoo",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.13,>=3.9",
"maintainer_email": "Daniel Han <danielhanchen@gmail.com>, Michael Han <info@unsloth.ai>",
"keywords": "ai, llm",
"author": "Unsloth AI team",
"author_email": "info@unsloth.ai",
"download_url": "https://files.pythonhosted.org/packages/ad/9e/a7775945d6b58443b951dc2b9a0c36c2a6ab7008077ff4bfbc65c0482a00/unsloth_zoo-2025.3.16.tar.gz",
"platform": null,
"description": "<div align=\"center\">\r\n\r\n <a href=\"https://unsloth.ai\"><picture>\r\n <source media=\"(prefers-color-scheme: dark)\" srcset=\"https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20logo%20white%20text.png\">\r\n <source media=\"(prefers-color-scheme: light)\" srcset=\"https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20logo%20black%20text.png\">\r\n <img alt=\"unsloth logo\" src=\"https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20logo%20black%20text.png\" height=\"110\" style=\"max-width: 100%;\">\r\n </picture></a>\r\n \r\n<a href=\"https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing\"><img src=\"https://raw.githubusercontent.com/unslothai/unsloth/main/images/start free finetune button.png\" height=\"48\"></a>\r\n<a href=\"https://discord.gg/unsloth\"><img src=\"https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord button.png\" height=\"48\"></a>\r\n<a href=\"https://ko-fi.com/unsloth\"><img src=\"https://raw.githubusercontent.com/unslothai/unsloth/main/images/buy me a coffee button.png\" height=\"48\"></a>\r\n\r\n### Unsloth Zoo - Utils for Unsloth!\r\n\r\n\r\n\r\n</div>\r\n\r\n## \u2728 Finetune for Free\r\n\r\nAll notebooks are **beginner friendly**! Add your dataset, click \"Run All\", and you'll get a 2x faster finetuned model which can be exported to GGUF, Ollama, vLLM or uploaded to Hugging Face.\r\n\r\n| Unsloth supports | Free Notebooks | Performance | Memory use |\r\n|-----------|---------|--------|----------|\r\n| **Llama 3.2 (3B)** | [\u25b6\ufe0f Start for free](https://colab.research.google.com/drive/1T5-zKWM_5OD21QHwXHiV9ixTRR7k3iB9?usp=sharing) | 2x faster | 60% less |\r\n| **Llama 3.1 (8B)** | [\u25b6\ufe0f Start for free](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) | 2x faster | 60% less |\r\n| **Phi-3.5 (mini)** | [\u25b6\ufe0f Start for free](https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing) | 2x faster | 50% less |\r\n| **Gemma 2 (9B)** | [\u25b6\ufe0f Start for free](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing) | 2x faster | 63% less |\r\n| **Mistral Small (22B)** | [\u25b6\ufe0f Start for free](https://colab.research.google.com/drive/1oCEHcED15DzL8xXGU1VTx5ZfOJM8WY01?usp=sharing) | 2x faster | 60% less |\r\n| **Ollama** | [\u25b6\ufe0f Start for free](https://colab.research.google.com/drive/1WZDi7APtQ9VsvOrQSSC5DDtxq159j8iZ?usp=sharing) | 1.9x faster | 43% less |\r\n| **Mistral v0.3 (7B)** | [\u25b6\ufe0f Start for free](https://colab.research.google.com/drive/1_yNCks4BTD5zOnjozppphh5GzMFaMKq_?usp=sharing) | 2.2x faster | 73% less |\r\n| **ORPO** | [\u25b6\ufe0f Start for free](https://colab.research.google.com/drive/11t4njE3c4Lxl-07OD8lJSMKkfyJml3Tn?usp=sharing) | 1.9x faster | 43% less |\r\n| **DPO Zephyr** | [\u25b6\ufe0f Start for free](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 43% less |\r\n\r\n- **Kaggle Notebooks** for [Llama 3.1 (8B)](https://www.kaggle.com/danielhanchen/kaggle-llama-3-1-8b-unsloth-notebook), [Gemma 2 (9B)](https://www.kaggle.com/code/danielhanchen/kaggle-gemma-7b-unsloth-notebook/), [Mistral (7B)](https://www.kaggle.com/code/danielhanchen/kaggle-mistral-7b-unsloth-notebook)\r\n- Run [Llama 3.2 1B 3B notebook](https://colab.research.google.com/drive/1hoHFpf7ROqk_oZHzxQdfPW9yvTxnvItq?usp=sharing) and [Llama 3.2 conversational notebook](https://colab.research.google.com/drive/1T5-zKWM_5OD21QHwXHiV9ixTRR7k3iB9?usp=sharing)\r\n- Run [Llama 3.1 conversational notebook](https://colab.research.google.com/drive/15OyFkGoCImV9dSsewU1wa2JuKB4-mDE_?usp=sharing) and [Mistral v0.3 ChatML](https://colab.research.google.com/drive/15F1xyn8497_dUbxZP4zWmPZ3PJx1Oymv?usp=sharing)\r\n- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for continued pretraining / raw text\r\n- This [continued pretraining notebook](https://colab.research.google.com/drive/1tEd1FrOXWMnCU9UIvdYhs61tkxdMuKZu?usp=sharing) is for learning another language\r\n- Click [here](https://github.com/unslothai/unsloth/wiki) for detailed documentation for Unsloth.\r\n\r\n\r\n## \ud83d\udd17 Links and Resources\r\n| Type | Links |\r\n| ------------------------------- | --------------------------------------- |\r\n| \ud83d\udcda **Documentation & Wiki** | [Read Our Docs](https://docs.unsloth.ai) |\r\n| <img height=\"14\" src=\"https://upload.wikimedia.org/wikipedia/commons/6/6f/Logo_of_Twitter.svg\" /> **Twitter (aka X)** | [Follow us on X](https://twitter.com/unslothai)|\r\n| \ud83d\udcbe **Installation** | [unsloth/README.md](https://github.com/unslothai/unsloth/tree/main#-installation-instructions)|\r\n| \ud83e\udd47 **Benchmarking** | [Performance Tables](https://github.com/unslothai/unsloth/tree/main#-performance-benchmarking)\r\n| \ud83c\udf10 **Released Models** | [Unsloth Releases](https://huggingface.co/unsloth)|\r\n| \u270d\ufe0f **Blog** | [Read our Blogs](https://unsloth.ai/blog)|\r\n\r\n## \u2b50 Key Features\r\n- All kernels written in [OpenAI's Triton](https://openai.com/research/triton) language. **Manual backprop engine**.\r\n- **0% loss in accuracy** - no approximation methods - all exact.\r\n- No change of hardware. Supports NVIDIA GPUs since 2018+. Minimum CUDA Capability 7.0 (V100, T4, Titan V, RTX 20, 30, 40x, A100, H100, L40 etc) [Check your GPU!](https://developer.nvidia.com/cuda-gpus) GTX 1070, 1080 works, but is slow.\r\n- Works on **Linux** and **Windows** via WSL.\r\n- Supports 4bit and 16bit QLoRA / LoRA finetuning via [bitsandbytes](https://github.com/TimDettmers/bitsandbytes).\r\n- Open source trains 5x faster - see [Unsloth Pro](https://unsloth.ai/) for up to **30x faster training**!\r\n- If you trained a model with \ud83e\udda5Unsloth, you can use this cool sticker! <img src=\"https://raw.githubusercontent.com/unslothai/unsloth/main/images/made with unsloth.png\" height=\"50\" align=\"center\" />\r\n\r\n\r\n## \ud83d\udcbe Installation Instructions\r\n\r\nThese are utilities for [Unsloth](https://github.com/unslothai/unsloth), so install Unsloth as well! For stable releases for Unsloth Zoo, use `pip install unsloth_zoo`. We recommend `pip install \"unsloth_zoo @ git+https://github.com/unslothai/unsloth-zoo.git\"` for most installations though.\r\n\r\n```bash\r\npip install unsloth_zoo\r\n```\r\n\r\n## License\r\n\r\nUnsloth Zoo is licensed under the GNU Affero General Public License.\r\n",
"bugtrack_url": null,
"license": null,
"summary": "Utils for Unsloth",
"version": "2025.3.16",
"project_urls": {
"documentation": "https://github.com/unslothai/unsloth",
"homepage": "http://www.unsloth.ai",
"repository": "https://github.com/unslothai/unsloth"
},
"split_keywords": [
"ai",
" llm"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "ad97c6461fc80b667ca92c54b8f71f58208ef0452e355a008eaddcc94f6330f6",
"md5": "2567cd80f5bd6072ab1ec23d2d50f458",
"sha256": "5f48f13942096f7181d80ae5d8dd1b5b75d59f2df3c87e41cbd08457f09963ee"
},
"downloads": -1,
"filename": "unsloth_zoo-2025.3.16-py3-none-any.whl",
"has_sig": false,
"md5_digest": "2567cd80f5bd6072ab1ec23d2d50f458",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.13,>=3.9",
"size": 126916,
"upload_time": "2025-03-22T01:04:41",
"upload_time_iso_8601": "2025-03-22T01:04:41.801893Z",
"url": "https://files.pythonhosted.org/packages/ad/97/c6461fc80b667ca92c54b8f71f58208ef0452e355a008eaddcc94f6330f6/unsloth_zoo-2025.3.16-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "ad9ea7775945d6b58443b951dc2b9a0c36c2a6ab7008077ff4bfbc65c0482a00",
"md5": "4cf9f019d7651e17cc189dac0667d649",
"sha256": "bbf3995f4cd506037a8525acd7d3fed548557371562d82b27d8a4f9d2f95b6a3"
},
"downloads": -1,
"filename": "unsloth_zoo-2025.3.16.tar.gz",
"has_sig": false,
"md5_digest": "4cf9f019d7651e17cc189dac0667d649",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.13,>=3.9",
"size": 113262,
"upload_time": "2025-03-22T01:04:43",
"upload_time_iso_8601": "2025-03-22T01:04:43.304885Z",
"url": "https://files.pythonhosted.org/packages/ad/9e/a7775945d6b58443b951dc2b9a0c36c2a6ab7008077ff4bfbc65c0482a00/unsloth_zoo-2025.3.16.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-03-22 01:04:43",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "unslothai",
"github_project": "unsloth",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "unsloth-zoo"
}
